Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 87566
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    omens
    -0.08
    isman
    -0.06
    lander
    -0.06
    obus
    -0.06
    à¸Ńà¸Ķ
    -0.06
    ulti
    -0.06
    apan
    -0.06
    omers
    -0.06
    ãĥ³ãĥIJ
    -0.06
    entine
    -0.06
    POSITIVE LOGITS
    ÙĬØ«
    0.07
    iyan
    0.07
    æĪª
    0.06
    γοÏħ
    0.06
    ius
    0.06
    ephir
    0.06
    vyk
    0.06
    iked
    0.06
    250
    0.06
     Pods
    0.06
    Activations Density 0.090%

    No Known Activations